因为做个实验，需要北京市所有公交车站点的经纬度，就使用爬虫爬取了一下，为了加快速度用到了python 多进程，用这个代码爬取其他市的公交车站经纬度也是可行的。步骤分为两块，首先爬取北京市公交车站点的名称，然后调用百度的地址解析API爬取站点的经纬度。结果及代码https://github.com/FFGF/BeiJIngBusStation

爬取北京市公交车站点

爬取线路名称

从这个https://beijing.8684.cn/网址爬取名称，先爬取线路名称，再爬取每条线路对应的站名

lineName

stationName

代码如下,将爬取的线路存储为pick文件

import requests
import pandas as pd
import pickle
import os

from bs4 import BeautifulSoup

def readData(filePath):
    with open(filePath, 'rb') as f:
        return pickle.load(f)

def writeData(filePath, data):
    with open(filePath, 'wb') as f:
        pickle.dump(data, f)

baseUrl = 'https://beijing.8684.cn'
urlList = ['1', '2', '3', '4', '5', '6', '7', '8', '9', 'B', 'C', 'D', 'F', 'G', 'H', 'K', 'L', 'M', 'P', 'S', 'T', 'X', 'Y', 'Z']

def getBusLineName():
    """爬取北京市公交车线路名称
    :return:
    """
    result = []
    for url in urlList:
        tempUrl = baseUrl + "/list" + url
        html = requests.get(tempUrl)
        soup = BeautifulSoup(html.text, "html.parser")
        aTag = soup.select(".list > a")
        for a in aTag:
            result.append([a.text, a['href']])
    return result

busLines = getBusLineName()
busLinesPd = pd.DataFrame(columns=['lineName', 'url'], data=busLines)

if os.path.exists('/data/busLinesPd.pkl'):
    writeData('./data/busLinesPd.pkl', busLinesPd)

爬取站点名称

代码如下,将结果存储到数据库中，如果爬取过程中报错，就再运行一次，已经爬取的数据会被过滤掉，只会爬取未爬取的数据。会在数据库中存储一个站点多次，因为一个站点出现在不同线路中，等爬取经纬度的时候去重即可。

import requests
import pickle
import time
import random
from bs4 import BeautifulSoup
import MySQLdb
from multiprocessing import Pool

def readData(filePath):
    """读取pickle文件
    :param filePath: 文件路径
    :return:
    """
    with open(filePath, 'rb') as f:
        return pickle.load(f)

def writeData(filePath, data):
    """将data写入到filePath
    :param filePath: 路径
    :param data: 数据
    :return:
    """
    with open(filePath, 'wb') as f:
        pickle.dump(data, f)

def writeMySql(data):
    """向数据库批量写入数据
    :param data: [[],[],[]...]
    :return:
    """
    db = MySQLdb.connect("localhost", "root", "", "busstation", charset='utf8')
    cursor = db.cursor()
    sql = """
    INSERT INTO stationname(line_name, url, station_name)
    VALUES (%s, %s, %s)
    """
    cursor.executemany(sql, data)
    db.commit()
    cursor.close()
    db.close()
    return

def getExistLines():
    """获得已经写入数据库的公交站数据
    :return:
    """
    db = MySQLdb.connect("localhost", "root", "", "busstation", charset='utf8')
    cursor = db.cursor()

    sql = """
    select distinct(line_name) from stationname;
    """
    cursor.execute(sql)
    results = cursor.fetchall()
    db.commit()
    cursor.close()
    db.close()
    return results

baseUrl = 'https://beijing.8684.cn'

def getBusStationName(line):
    """获取每条线路line的公交车站名然后写入数据库
    :param line: 公交线路名称
    :return:
    """
    result = []
    tempUrl = baseUrl + line[1]
    try:
        # 随机休眠1-5秒，防止被拒绝
        time.sleep(random.randint(1, 5))
        html = requests.get(tempUrl)
    except:
        # 休眠20秒
        time.sleep(20)
        getBusStationName(line)
    soup = BeautifulSoup(html.text, "html.parser")
    liTag = soup.select(".bus-lzlist")[0].find_all("li")
    for li in liTag:
        result.append([line[0], line[1], li.text])
    writeMySql(result)
    print(line[0], line[1])
    return


if __name__ == '__main__':
    wait_crawl = []
    existLines = getExistLines()
    existLines = [item[0] for item in existLines]
    busLinesPd = readData('./data/busLinesPd.pkl')
    # 将已经爬取的线路排除，爬取未爬取的数据，我本机需要运行这个函数两次，第一次爬取了一千八百多个线路，第二次爬取一百多个。一共一千九百多个线路
    for item in busLinesPd.values:
        if item[0] in existLines:
            continue
        wait_crawl.append([item[0], item[1]])
    p = Pool(4)
    p.map(getBusStationName, wait_crawl)

数据库文件

数据库名称为busstation，有两个表，一个存储站点，一个存储站点经纬度

busstation

建表语句

CREATE TABLE `station_latlong` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `station_name` varchar(255) DEFAULT NULL,
  `lat` varchar(255) DEFAULT NULL,
  `lng` varchar(255) DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=14066 DEFAULT CHARSET=utf8mb4;

CREATE TABLE `stationname` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `line_name` varchar(255) DEFAULT NULL,
  `url` varchar(255) DEFAULT NULL,
  `station_name` varchar(255) DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=50768 DEFAULT CHARSET=utf8mb4;

爬取北京市公交车站点对应的经纬度

代码如下

import requests
import time
import MySQLdb
from multiprocessing import Pool, Queue

def getStationName():
    """获取公交站名称
    :return:
    """
    db = MySQLdb.connect("localhost", "root", "", "busstation", charset="utf8")
    cursor = db.cursor()
    sql = """
    select distinct(station_name) from stationname
    """
    cursor.execute(sql)
    results = cursor.fetchall()
    cursor.close()
    db.close()
    return results

def getExistStation():
    """获得已经写入数据库的公交站数据
    :return:
    """
    db = MySQLdb.connect("localhost", "root", "", "busstation", charset='utf8')
    cursor = db.cursor()

    sql = """
   select distinct(station_name) from station_latlong
    """
    cursor.execute(sql)
    results = cursor.fetchall()
    db.commit()
    cursor.close()
    db.close()
    return results

def writeMySql(queue):
    """向数据库批量写入数据
    :param data: [[],[],[]...]
    :return:
    """
    data = []
    while not queue.empty():
        data.append(queue.get())
    db = MySQLdb.connect("localhost", "root", "", "busstation", charset='utf8')
    cursor = db.cursor()
    sql = """
    INSERT INTO station_latlong(station_name, lat, lng)
    VALUES (%s, %s, %s)
    """
    cursor.executemany(sql, data)
    db.commit()
    cursor.close()
    db.close()
    return

queues = [Queue() for _ in range(5)]

def getStationLatLong(station):
    index = station[0]
    stationName = "北京市" + station[1] + "公交车站"
    urlTemplate = "http://api.map.baidu.com/geocoding/v3/?address={}&output=json&ak=你自己的ak&city=北京市'"
    # random.randint(1,5)
    html = requests.get(urlTemplate.format(stationName))

    latLongJson = html.json()['result']
    lat = latLongJson['location']['lat']
    long = latLongJson['location']['lng']
    queue = queues[index % 5]
    queue.put([station[1], lat, long])
    if queue.qsize() == 20: # 最开始的时候可以设置20，到最后几十条数据的时候需要设置为1
        writeMySql(queue)
        time.sleep(3)

if __name__ == '__main__':
    pool = Pool(4)
    stationNames = getStationName()
    stationNames = set(item[0] for item in stationNames)
    existStations = getExistStation()
    existStations = set(item[0] for item in existStations)
    wait_crawl = stationNames - existStations

    stationNames = [[i,v] for i, v in enumerate(wait_crawl)]
    pool.map(getStationLatLong, stationNames)

代码解释，我电脑有4个CPU所以开启四个进程，查看自己电脑CPU个数os.cpu_count()，然后为了加快插入数据库插入，创建5个Queue,然后队列满20个，批量插入到数据库。这样到数据最后只剩下一百条的时候你手动把代码if queue.qsize() == 20: 修改为if queue.qsize() == 1:即可。然后记得把代码urlTemplate = "http://api.map.baidu.com/geocoding/v3/?address={}&output=json&ak=你自己的ak&city=北京市'"，修改为自己的ak

获取百度ak

创建，把刚刚创建的复制出来即可获取一个ak可以爬取六千条左右，再多了就要认证了，所以找同学借个账号，再爬。

image.png

结果

stationname

station_latlong

爬取北京市所有公交车站点经纬度